Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    action verbs in contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     и
    1.09
     ਅਤੇ
    1.02
     و
    0.99
     અને
    0.93
     এবং
    0.90
     आणि
    0.90
     እና
    0.87
     và
    0.85
     και
    0.85
    했고
    0.82
    POSITIVE LOGITS
     in
    0.73
     Services
    0.71
     Partners
    0.70
     Snakes
    0.70
     Management
    0.69
     Problems
    0.69
     Team
    0.68
     whatnot
    0.68
     Power
    0.67
     Standard
    0.67
    Act Density 0.303%

    No Known Activations